Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2200 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.8097. Min Act: -0.1700
Data Index: 1669422 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.6222. Min Act: -0.1700
Data Index: 1342784 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.5284. Min Act: -0.1700
Data Index: 6311217 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.4034. Min Act: -0.1700
Data Index: 1845775 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.3409. Min Act: -0.1700
Data Index: 772177 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.2784. Min Act: -0.1700
Data Index: 3851362 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.2472. Min Act: -0.1700
Data Index: 5723469 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.2472. Min Act: -0.1700
Data Index: 1652975 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.2784. Min Act: -0.1700
Data Index: 5044145 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.2784. Min Act: -0.1700
Data Index: 4136674 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.2159. Min Act: -0.1700
Data Index: 6168834 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.1847. Min Act: -0.1700
Data Index: 6781219 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.2472. Min Act: -0.1700
Data Index: 6674230 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.1847. Min Act: -0.1700
Data Index: 6200893 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.1847. Min Act: -0.1700
Data Index: 8571137 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.1534. Min Act: -0.1700
Data Index: 3320743 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.1534. Min Act: -0.1700
Data Index: 8123779 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.0597. Min Act: -0.1700
Data Index: 5901593 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.0909. Min Act: -0.1700
Data Index: 6809663 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8097. Min Range: -6.8097
Max Act: 6.1534. Min Act: -0.1700
Data Index: 5710722 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19